Pith Number

pith:S4UISSUI

pith:2026:S4UISSUIKYF6QDZW4C7OPCRKOG

not attested not anchored not stored refs resolved

Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution

Chenchen Liu, Chenyu Wang, Chong Zheng, Han Li, Jiaheng Liu, Jinyu Tian, Letian Zhu, Rili Feng, Shihao Li, Weihao Xie, Xinping Lei, Yifan Yao, Yuqiao Du

Solvita achieves state-of-the-art results in competitive programming by letting LLM agents continuously learn from past outcomes using updatable knowledge networks.

arxiv:2605.15301 v1 · 2026-05-14 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{S4UISSUIKYF6QDZW4C7OPCRKOG}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Solvita establishes a new state-of-the-art among code-generation agents, outperforming existing multi-agent pipelines and nearly doubling the accuracy of single-pass baselines.

C2weakest assumption

That outcome signals such as pass/fail verdicts, test certification quality, and adversarial vulnerabilities can be recast as effective reinforcement learning updates to the graph-structured knowledge network weights to produce transferable reasoning experience.

C3one line summary

Solvita is an agentic evolution system using Planner, Solver, Oracle, and Hacker agents with trainable graph knowledge networks updated by reinforcement learning on pass/fail and vulnerability signals to achieve SOTA code generation performance.

References

130 extracted · 130 resolved · 11 Pith anchors

[1] Competition-level code generation with AlphaCode.Science, 378(6624):1092–1097 2022

[2] Measuring coding challenge competence with APPS 2021

[3] Can language models solve olympiad programming?arXiv preprint arXiv:2404.10952, 2024 2024

[4] LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code 2024 · arXiv:2403.07974

[5] Evaluating Large Language Models Trained on Code 2021 · arXiv:2107.03374

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:51.610145Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9728894a88560be80f36e0bee78a2a71b274dce595a03a03dce790586a083fdb

Aliases

arxiv: 2605.15301 · arxiv_version: 2605.15301v1 · doi: 10.48550/arxiv.2605.15301 · pith_short_12: S4UISSUIKYF6 · pith_short_16: S4UISSUIKYF6QDZW · pith_short_8: S4UISSUI

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/S4UISSUIKYF6QDZW4C7OPCRKOG \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9728894a88560be80f36e0bee78a2a71b274dce595a03a03dce790586a083fdb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ef14b2524be4c23e7e7f0bfc293f5059018f0744526972431bcea2a3a3c7e19e",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T18:15:09Z",
    "title_canon_sha256": "d34b07cc836d56f8d823a4b728f7102f266f80326af7d78f3c2fd356132cf115"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15301",
    "kind": "arxiv",
    "version": 1
  }
}